DPTNet (Libri1Mix speech enhancement pre-trained)

Reported on 2 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Speech2 results

Speech SeparationonWSJ0-2mix
SDRi· uses extra data· 2020-10-29
21.5
best: 25.2 (TF-Locoformer (L) + DM)
Stabilizing Label Assignment for Speech Separation by Self-supervised Pre-training arXiv:2010.15366
Speech SeparationonWSJ0-2mix
SI-SDRi· uses extra data· 2020-10-29
21.3
best: 25.1 (TF-Locoformer (L) + DM)
Stabilizing Label Assignment for Speech Separation by Self-supervised Pre-training arXiv:2010.15366